资源分类
》 资源 》论文》Affine-Invariant Online Optimization and the Low-rank Experts Problem

Affine-Invariant Online Optimization and the Low-rank Experts Problem

2020-02-10 | |  41 |   42 |   0

Abstract 

We present a new affine-invariant optimization algorithm called Online Lazy Newton. The regret of Online Lazy Newton is independent of conditioning: the algorithm’s performance depends on the best possible preconditioning of the problem in retrospect and on its intrinsic dimensionality. As an application, we?show how Online Lazy Newton can be used to achieve ? an optimal regret of order rT for the low-rank experts problem, improving by a r factor over the previously best known bound and resolving an open problem posed by Hazan et al. [15].

上一篇：Solving Most Systems of Random Quadratic Equations

下一篇：Model evidence from nonequilibrium simulations

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...